
#imported the required libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import psycopg2
import http.client
import folium
import plotly.graph_objs as go
import plotly.offline as pyo
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import LinearRegression
from sklearn.svm import SVR
import warnings
warnings.filterwarnings('ignore')


#read csv file which is stored in github repository
data = pd.read_csv('https://raw.githubusercontent.com/ravi2248/AIM-5001/main/Air_Quality.csv')


#we can see the top 5 rows
data.head()


#we can see the bottom 5 rows
data.tail()


#it will show the number of columns and rows in the dataset
data.shape

(18025, 12)


#we can see the columns details
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 18025 entries, 0 to 18024
Data columns (total 12 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Unique ID       18025 non-null  int64  
 1   Indicator ID    18025 non-null  int64  
 2   Name            18025 non-null  object 
 3   Measure         18025 non-null  object 
 4   Measure Info    18025 non-null  object 
 5   Geo Type Name   18025 non-null  object 
 6   Geo Join ID     18016 non-null  float64
 7   Geo Place Name  18016 non-null  object 
 8   Time Period     18025 non-null  object 
 9   Start_Date      18025 non-null  object 
 10  Data Value      18025 non-null  float64
 11  Message         0 non-null      float64
dtypes: float64(3), int64(2), object(7)
memory usage: 1.7+ MB


#here we are connecting the postgresql
#to read the data present in the database
con = psycopg2.connect(
    dbname = 'airquality',
    user = 'postgres',
    password = 'Ravi1234@',
    host = 'localhost',
    port = '5432'
)


#this query will return all the data stored in postgresql
query = "SELECT * FROM air_quality"


#we need to use read_sql func from pandas to read the data and stored it
global_data = pd.read_sql(query, con)


#we closed the connection after stored it
con.close()


#we can see the top 5 rows
global_data.head()


#we can see the bottom 5 rows
global_data.tail()


#it will show the number of columns and rows in the dataset
global_data.shape

(9450, 17)


#we can see the columns details
global_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9450 entries, 0 to 9449
Data columns (total 17 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   indicatorcode         9450 non-null   object 
 1   indicator             9450 non-null   object 
 2   parentlocationcode    9450 non-null   object 
 3   parentlocation        9450 non-null   object 
 4   locationtype          9450 non-null   object 
 5   spatialdimvaluecode   9450 non-null   object 
 6   location              9450 non-null   object 
 7   periodtype            9450 non-null   object 
 8   period                9450 non-null   object 
 9   islatestyear          9450 non-null   bool   
 10  dim1type              9450 non-null   object 
 11  dim1                  9450 non-null   object 
 12  dim1valuecode         9450 non-null   object 
 13  factvaluenumeric      9450 non-null   float64
 14  factvaluenumericlow   9450 non-null   float64
 15  factvaluenumerichigh  9450 non-null   float64
 16  value                 9450 non-null   object 
dtypes: bool(1), float64(3), object(13)
memory usage: 1.2+ MB


#Here we can see the unique names of indicators and there frequency in the dataset
data['Name'].value_counts()

Name
Nitrogen dioxide (NO2)                                    5922
Fine particles (PM 2.5)                                   5922
Ozone (O3)                                                2115
Asthma emergency departments visits due to Ozone           485
Asthma hospitalizations due to Ozone                       484
Asthma emergency department visits due to PM2.5            480
Annual vehicle miles traveled (cars)                       321
Annual vehicle miles traveled                              321
Annual vehicle miles traveled (trucks)                     321
Respiratory hospitalizations due to PM2.5 (age 20+)        240
Cardiovascular hospitalizations due to PM2.5 (age 40+)     240
Cardiac and respiratory deaths due to Ozone                240
Deaths due to PM2.5                                        240
Outdoor Air Toxics - Benzene                               203
Outdoor Air Toxics - Formaldehyde                          203
Boiler Emissions- Total SO2 Emissions                       96
Boiler Emissions- Total NOx Emissions                       96
Boiler Emissions- Total PM2.5 Emissions                     96
Name: count, dtype: int64


#It will plot a bar graph
#we can see the names of indicators and their frequencies
plt.figure(figsize = (10, 8))
data['Name'].value_counts().plot(kind = 'bar', color = 'lightgreen')
plt.xlabel('Name')
plt.ylabel('Frequency')
plt.xticks(rotation = 45, ha = 'right')
plt.tight_layout()
plt.show()


#Here we can see the frequencies of type of geographic data
data['Geo Type Name'].value_counts()

Geo Type Name
UHF42       7140
CD          6490
UHF34       3366
Borough      859
Citywide     170
Name: count, dtype: int64


#It will plot a bar graph
#we can see the types of geographic areas and their frequencies
plt.figure(figsize = (10, 6))
data['Geo Type Name'].value_counts().plot(kind = 'bar', color = 'skyblue')
plt.xlabel('Geo Type Name')
plt.ylabel('Frequency')
plt.xticks(rotation = 45, ha = 'right')
plt.tight_layout()
plt.show()


#Here we are getting the data of the indicator named Fine particles (PM 2.5)
pm2_5_data = data[data['Name'] == 'Fine particles (PM 2.5)']


#Here we are changing the data type to datetime
pm2_5_data['Start_Date'] = pd.to_datetime(pm2_5_data['Start_Date'])


#It will plot PM 2.5 concentration over time
#on x-axis we can see time and on y-axis we can see PM 2.5 concentration
plt.figure(figsize = (10, 6))
plt.plot(pm2_5_data['Start_Date'], pm2_5_data['Data Value'], marker = 'o', linestyle = '', color = 'orange')
plt.title('Trend of PM2.5 Concentration Over Time')
plt.xlabel('Time')
plt.ylabel('PM2.5 Concentration (mcg/m3)')
plt.xticks(rotation = 45)
plt.grid(True)
plt.tight_layout()
plt.show()


#it shows a line plot
#we can see new york city air quality trends over time
plt.figure(figsize = (12, 6))
sns.lineplot(data = data, x = "Start_Date", y = "Data Value", hue = "Name", style = "Name", markers = True, dashes = False)
plt.title("New York City Air Quality Trends Over Time")
plt.xlabel("Date")
plt.ylabel("Data Value")
plt.xticks(rotation = 90)
plt.legend(title = "Indicator", bbox_to_anchor = (1, 1), loc = 'upper left')
plt.tight_layout()
plt.show()


#it will plot a boxplot graph
#it shows distribution of air quality across countries
plt.figure(figsize = (12, 6))
sns.boxplot(data = global_data, x = "parentlocation", y = "factvaluenumeric")
plt.title("Distribution of Air Quality Indicator Across Countries")
plt.xlabel("Country")
plt.ylabel("Data Value")
plt.xticks(rotation = 45)
plt.tight_layout()
plt.show()


#it plots a barplot
#it shows comparision of PM 2.5 Concentrations across major urban areas
plt.figure(figsize = (14, 8))
sns.barplot(data = data[data["Name"] == "Fine particles (PM 2.5)"], x = "Geo Place Name", y = "Data Value", ci = None)
plt.title("Comparison of PM 2.5 concentrations across major Urban Areas")
plt.xlabel("Urban Area")
plt.ylabel("Mean PM2.5 Concentration")
plt.xticks(rotation = 90)
plt.tight_layout()
plt.show()


#it shows a line plot
#we can see global air quality trends over time
plt.figure(figsize = (12, 6))
sns.lineplot(data = global_data, x = "period", y = "factvaluenumeric", hue = "parentlocation", style = "parentlocation", markers = True, dashes = False)
plt.title("Global Air Quality Trends over time")
plt.xlabel("Year")
plt.ylabel("Data Value")
plt.xticks(rotation = 45)
plt.legend(title = "Parent Location", bbox_to_anchor = (1, 1), loc = 'upper left')
plt.tight_layout()
plt.show()


#it shows a bar plot
#it shows maximum air quality indicators across global regions
plt.figure(figsize = (10, 6))
max_values = global_data.groupby("parentlocation")["factvaluenumeric"].max().sort_values(ascending=False)
sns.barplot(x = max_values.values, y = max_values.index, palette = "viridis")
plt.title("Maximum Air Quality Indicators Across Global Regions")
plt.xlabel("Maximum Data Value")
plt.ylabel("Region")
plt.tight_layout()
plt.show()


#here we fetch the values of countries and their PM2.5 concentration values
PM25_map_data = {
    'Country': global_data['location'],
    'Value': global_data['factvaluenumeric']
}


#we converted the data into dataframe
PM25_map_data = pd.DataFrame(PM25_map_data)


# Create choropleth map
map_data = dict(
        type = 'choropleth',
        locations = PM25_map_data['Country'],
        locationmode = 'country names',
        z = PM25_map_data['Value'],
        text = PM25_map_data['Country'],
        colorscale = 'Blues',
        colorbar = {'title' : 'Value'}
      )


layout = dict(title = 'PM2.5 Concentrations of global data',
              geo = dict(showframe = False, projection = {'type':'mercator'})
             )


choromap = go.Figure(data = [map_data],layout = layout)


choromap


#Here we are trying to connect the api which has present info of NYC
conn = http.client.HTTPSConnection("api.ambeedata.com")

headers = {
    'x-api-key': "933a144f6ff91631a9dea379dc86e5d83e7454f735c4ed1d494f7acb7f07253f",
    'Content-type': "application/json"
    }

conn.request("GET", "/latest/by-lat-lng?lat=40.730610&lng=-73.935242", headers=headers)

res = conn.getresponse()
api_data = res.read()


#here we are decoding the data into utf-8
api_data = api_data.decode('utf-8')


#we can see the data
api_data

'{"message":"success","stations":[{"CO":0.531,"NO2":27.06,"OZONE":20.102,"PM10":49.87,"PM25":11.196,"SO2":0.564,"city":"New York","countryCode":"US","division":"New York","lat":40.7139,"lng":-74.007,"placeName":"Broadway","postalCode":"10007-0052","state":"New York","updatedAt":"2024-05-07T02:00:00.000Z","AQI":47,"aqiInfo":{"pollutant":"PM2.5","concentration":11.196,"category":"Good"}}]}'


#here we are importing the json library
import json


#we are loading the api string data to convert it into dictionary
api_data = json.loads(api_data)


#here we can see it
api_data

{'message': 'success',
 'stations': [{'CO': 0.531,
   'NO2': 27.06,
   'OZONE': 20.102,
   'PM10': 49.87,
   'PM25': 11.196,
   'SO2': 0.564,
   'city': 'New York',
   'countryCode': 'US',
   'division': 'New York',
   'lat': 40.7139,
   'lng': -74.007,
   'placeName': 'Broadway',
   'postalCode': '10007-0052',
   'state': 'New York',
   'updatedAt': '2024-05-07T02:00:00.000Z',
   'AQI': 47,
   'aqiInfo': {'pollutant': 'PM2.5',
    'concentration': 11.196,
    'category': 'Good'}}]}


#Here we separated the above api data took values of latitude, longitude, and PM 2.5
ny_present_data = {
    'Latitude': [api_data['stations'][0]['lat']],
    'Longitude': [api_data['stations'][0]['lng']],
    'PM2.5': [api_data['stations'][0]['PM25']]
}


#Here we converted into dataframe
ny_present_data = pd.DataFrame(ny_present_data)


#it will create a map centered around NYC
nyc_map = folium.Map(location = [api_data['stations'][0]['lat'], api_data['stations'][0]['lng']], zoom_start = 10)


#here we are adding markers for the data point
for index, row in ny_present_data.iterrows():
    folium.CircleMarker(
        location = [row['Latitude'], row['Longitude']],
        radius = row['PM2.5'],
        color = 'red',
        fill = True,
        fill_color = 'red',
        fill_opacity = 1,
        popup = f"PM2.5: {row['PM2.5']} µg/m³"
    ).add_to(nyc_map)


#we can see the map
nyc_map


#here we can see the total null values of ny data columns
data.isnull().sum()

Unique ID             0
Indicator ID          0
Name                  0
Measure               0
Measure Info          0
Geo Type Name         0
Geo Join ID           9
Geo Place Name        9
Time Period           0
Start_Date            0
Data Value            0
Message           18025
dtype: int64


#Here we are counting the unique values of Message column
data['Message'].value_counts()

Series([], Name: count, dtype: int64)


#we are dropping the column named Message
data = data.drop(columns = ['Message'])


#we can see the top 5 rows after dropping
data.head()


#we can see the total null values of ny data columns
data.isnull().sum()

Unique ID         0
Indicator ID      0
Name              0
Measure           0
Measure Info      0
Geo Type Name     0
Geo Join ID       9
Geo Place Name    9
Time Period       0
Start_Date        0
Data Value        0
dtype: int64


#Here we are dropping rows which has Geo join ID or Geo Place Name values are null
data.dropna(subset = ['Geo Join ID', 'Geo Place Name'], inplace = True)


#now we can see that there is no missing data in the dataset of ny
data.isnull().sum()

Unique ID         0
Indicator ID      0
Name              0
Measure           0
Measure Info      0
Geo Type Name     0
Geo Join ID       0
Geo Place Name    0
Time Period       0
Start_Date        0
Data Value        0
dtype: int64


#here we can see the total null values of global data columns
global_data.isnull().sum()

indicatorcode           0
indicator               0
parentlocationcode      0
parentlocation          0
locationtype            0
spatialdimvaluecode     0
location                0
periodtype              0
period                  0
islatestyear            0
dim1type                0
dim1                    0
dim1valuecode           0
factvaluenumeric        0
factvaluenumericlow     0
factvaluenumerichigh    0
value                   0
dtype: int64


#Here we are extracting features like year from time period data
data['year'] = pd.to_datetime(data['Time Period'], errors = 'coerce').dt.year


#Here we are extracting features like month from time period data
data['month'] = pd.to_datetime(data['Time Period'], errors = 'coerce').dt.month


#we are dropping the null values before building predictive model
data.dropna(inplace = True)


#we are splitting the data into independent and dependent variable
X = data[['Indicator ID', 'Geo Type Name', 'Geo Place Name', 'year', 'month']]
y = data['Data Value']


#Here we are encoding the categorical variables
X = pd.get_dummies(X)


#we are spliting the data into training 80% and testing 20%.  
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)


#making a model of RandomForest
model = RandomForestRegressor()


#we are training the model
model.fit(X_train, y_train)

RandomForestRegressor()

RandomForestRegressor()


#Here we are getting predictions
predictions = model.predict(X_test)


#we are calculating the mean squared error which tell us about the model performance
mse = mean_squared_error(y_test, predictions)


#we can see the mean squared error
mse

74.57973174397588


#it plots a scatter plot 
#we can see the distribution of actual values and predicted values 
plt.figure(figsize = (8, 6))
plt.scatter(y_test, predictions)
plt.xlabel('Actual')
plt.ylabel('Predicted')
plt.title('Actual vs. Predicted')
plt.show()


#here we can see the top 5 rows
data.head()


#we can see the bottom 5 rows
data.tail()


#here we can see the decription of the columns
data.describe()


#here we can see the info of the data
data.info()

<class 'pandas.core.frame.DataFrame'>
Index: 1657 entries, 0 to 18024
Data columns (total 13 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Unique ID       1657 non-null   int64  
 1   Indicator ID    1657 non-null   int64  
 2   Name            1657 non-null   object 
 3   Measure         1657 non-null   object 
 4   Measure Info    1657 non-null   object 
 5   Geo Type Name   1657 non-null   object 
 6   Geo Join ID     1657 non-null   float64
 7   Geo Place Name  1657 non-null   object 
 8   Time Period     1657 non-null   object 
 9   Start_Date      1657 non-null   object 
 10  Data Value      1657 non-null   float64
 11  year            1657 non-null   float64
 12  month           1657 non-null   float64
dtypes: float64(4), int64(2), object(7)
memory usage: 181.2+ KB


#it plots a scatter plot
#we can see the scatter plot of Indicator ID and Data value
plt.figure(figsize = (12, 6))
plt.scatter(data['Indicator ID'], data['Data Value'])
plt.xlabel('Indicator ID')
plt.ylabel('Data Value')
plt.title('Scatter Plot of Indicator ID vs. Data Value')
plt.show()


#it plots a scatter plot
#we can see the data values over changing years
plt.scatter(data['year'], data['Data Value'])
plt.xlabel('Years')
plt.ylabel('Data Value')
plt.title('Scatter Plot of Years vs. Data Value')
plt.show()


#we are splitting the data into independent and dependent variable
X = data[['Indicator ID', 'Geo Type Name', 'Geo Place Name', 'year', 'month']]
y = data['Data Value']


#Here we are encoding the categorical variables
X = pd.get_dummies(X)


#we are spliting the data into training 80% and testing 20%.  
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)


#making a model of Linear Regression
model = LinearRegression()


#we are training the model
model.fit(X_train, y_train)

LinearRegression()

LinearRegression()


#Here we are getting predictions
predictions = model.predict(X_test)


#we are calculating the mean squared error which tell us about the model performance
mse = mean_squared_error(y_test, predictions)


#we can see the mean squared error
mse

1337.7076638095348


#it plots a scatter plot 
#we can see the distribution of actual values and predicted values 
plt.figure(figsize = (8, 6))
plt.scatter(y_test, predictions)
plt.xlabel('Actual')
plt.ylabel('Predicted')
plt.title('Actual vs. Predicted')
plt.show()


#we are splitting the data into independent and dependent variable
X = data[['Indicator ID', 'Geo Type Name', 'Geo Place Name', 'year', 'month']]
y = data['Data Value']


#Here we are encoding the categorical variables
X = pd.get_dummies(X)


#we are spliting the data into training 80% and testing 20%.
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)


#making a model of Support Vector Regression
model = SVR(kernel='rbf')


#we are training the model
model.fit(X_train, y_train)

SVR()

SVR()


#Here we are getting predictions
predictions = model.predict(X_test)


#we are calculating the mean squared error which tell us about the model performance
mse = mean_squared_error(y_test, predictions)


#we can see the mean squared error
mse

2094.799139328058


#it plots a scatter plot 
#we can see the distribution of actual values and predicted values 
plt.figure(figsize = (8, 6))
plt.scatter(y_test, predictions)
plt.xlabel('Actual')
plt.ylabel('Predicted')
plt.title('Actual vs. Predicted')
plt.show()

	Unique ID	Indicator ID	Name	Measure	Measure Info	Geo Type Name	Geo Join ID	Geo Place Name	Time Period	Start_Date	Data Value	Message
0	179772	640	Boiler Emissions- Total SO2 Emissions	Number per km2	number	UHF42	409.0	Southeast Queens	2015	01/01/2015	0.3	NaN
1	179785	640	Boiler Emissions- Total SO2 Emissions	Number per km2	number	UHF42	209.0	Bensonhurst - Bay Ridge	2015	01/01/2015	1.2	NaN
2	178540	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	209.0	Bensonhurst - Bay Ridge	Annual Average 2012	12/01/2011	8.6	NaN
3	178561	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	409.0	Southeast Queens	Annual Average 2012	12/01/2011	8.0	NaN
4	823217	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	409.0	Southeast Queens	Summer 2022	06/01/2022	6.1	NaN

	Unique ID	Indicator ID	Name	Measure	Measure Info	Geo Type Name	Geo Join ID	Geo Place Name	Time Period	Start_Date	Data Value	Message
18020	816914	643	Annual vehicle miles traveled	Million miles	per square mile	CD	503.0	Tottenville and Great Kills (CD3)	2019	01/01/2019	12.9	NaN
18021	816913	643	Annual vehicle miles traveled	Million miles	per square mile	CD	503.0	Tottenville and Great Kills (CD3)	2010	01/01/2010	14.7	NaN
18022	816872	643	Annual vehicle miles traveled	Million miles	per square mile	UHF42	208.0	Canarsie - Flatlands	2010	01/01/2010	43.4	NaN
18023	816832	643	Annual vehicle miles traveled	Million miles	per square mile	UHF42	407.0	Southwest Queens	2010	01/01/2010	65.8	NaN
18024	151658	643	Annual vehicle miles traveled	Million miles	per square mile	UHF42	408.0	Jamaica	2005	01/01/2005	41.0	NaN

	indicatorcode	indicator	parentlocationcode	parentlocation	locationtype	spatialdimvaluecode	location	periodtype	period	islatestyear	dim1type	dim1	dim1valuecode	factvaluenumeric	factvaluenumericlow	factvaluenumerichigh	value
0	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AFR	Africa	Country	KEN	Kenya	Year	2019	True	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	10.01	6.29	13.74	10.01 [6.29-13.74]
1	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	TTO	Trinidad and Tobago	Year	2019	True	Residence Area Type	Rural	RESIDENCEAREATYPE_RUR	10.02	7.44	12.55	10.02 [7.44-12.55]
2	SDGPM25	Concentrations of fine particulate matter (PM2.5)	EUR	Europe	Country	GBR	United Kingdom of Great Britain and Northern I...	Year	2019	True	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	10.06	9.73	10.39	10.06 [9.73-10.39]
3	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	GRD	Grenada	Year	2019	True	Residence Area Type	Total	RESIDENCEAREATYPE_TOTL	10.08	7.07	13.20	10.08 [7.07-13.20]
4	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	BRA	Brazil	Year	2019	True	Residence Area Type	Towns	RESIDENCEAREATYPE_TOWN	10.09	8.23	12.46	10.09 [8.23-12.46]

	indicatorcode	indicator	parentlocationcode	parentlocation	locationtype	spatialdimvaluecode	location	periodtype	period	islatestyear	dim1type	dim1	dim1valuecode	factvaluenumeric	factvaluenumericlow	factvaluenumerichigh	value
9445	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	BLZ	Belize	Year	2010	False	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	9.92	3.91	20.28	9.92 [3.91-20.28]
9446	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	TTO	Trinidad and Tobago	Year	2010	False	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	9.92	7.80	12.89	9.92 [7.80-12.89]
9447	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AFR	Africa	Country	KEN	Kenya	Year	2010	False	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	9.94	6.30	13.57	9.94 [6.30-13.57]
9448	SDGPM25	Concentrations of fine particulate matter (PM2.5)	AMR	Americas	Country	USA	United States of America	Year	2010	False	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	9.95	9.78	10.11	9.95 [9.78-10.11]
9449	SDGPM25	Concentrations of fine particulate matter (PM2.5)	EMR	Eastern Mediterranean	Country	AFG	Afghanistan	Year	2010	False	Residence Area Type	Cities	RESIDENCEAREATYPE_CITY	92.79	66.17	128.40	92.79 [66.17-128.44]

	Unique ID	Indicator ID	Name	Measure	Measure Info	Geo Type Name	Geo Join ID	Geo Place Name	Time Period	Start_Date	Data Value
0	179772	640	Boiler Emissions- Total SO2 Emissions	Number per km2	number	UHF42	409.0	Southeast Queens	2015	01/01/2015	0.3
1	179785	640	Boiler Emissions- Total SO2 Emissions	Number per km2	number	UHF42	209.0	Bensonhurst - Bay Ridge	2015	01/01/2015	1.2
2	178540	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	209.0	Bensonhurst - Bay Ridge	Annual Average 2012	12/01/2011	8.6
3	178561	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	409.0	Southeast Queens	Annual Average 2012	12/01/2011	8.0
4	823217	365	Fine particles (PM 2.5)	Mean	mcg/m3	UHF42	409.0	Southeast Queens	Summer 2022	06/01/2022	6.1

Analyzing Air Quality Trends: A Comparative Study of New York Neighborhoods and Global Standards

Abstract

Introduction

Research Approach

Exploratory Data Analysis

Data Preparation

Prepped Data Analysis

Investigative Analysis and Results

Conclusion

	Unique ID	Indicator ID	Geo Join ID	Data Value	year	month
count	1657.000000	1657.000000	1657.000000	1657.000000	1657.000000	1657.0
mean	461609.864816	644.091129	263.517200	32.433736	2011.541340	1.0
std	319311.000973	1.911578	138.287712	42.480830	4.861327	0.0
min	130397.000000	640.000000	1.000000	0.000000	2005.000000	1.0
25%	154472.000000	643.000000	201.000000	1.900000	2005.000000	1.0
50%	315590.000000	644.000000	302.000000	6.100000	2011.000000	1.0
75%	816928.000000	645.000000	403.000000	56.600000	2015.000000	1.0
max	817342.000000	647.000000	504.000000	284.700000	2019.000000	1.0